© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 42895
    Prev
    Next
    INDEX
    Explanations

    references to art supplies and associated expenses in creative projects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Juliushanhanhan/llama-3-8b-it-res/blocks.25.hook_resid_post
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    gated
    Context Size
    1,024
    Dataset
    Juliushanhanhan/openwebtext-1b-llama3-tokenized-cxt-1024
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ovol
    -0.17
    asser
    -0.15
    ajas
    -0.15
    rada
    -0.14
    aser
    -0.14
     QRect
    -0.14
    lez
    -0.14
     uphol
    -0.14
    niÄį
    -0.13
     تÙĥÙĬÙĬÙģ
    -0.13
    POSITIVE LOGITS
     supplies
    0.80
     Supplies
    0.69
     materials
    0.67
     Materials
    0.56
     supply
    0.54
    Materials
    0.53
    materials
    0.52
     Supply
    0.51
    supply
    0.46
    Supply
    0.45
    Activations Density 0.016%

    No Known Activations